int is_start(unsigned char *seq, int n, struct _training *tinf) {
/* ATG */
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1) return 1;
/* Codes that only use ATG */
if(tinf->trans_table == 6 || tinf->trans_table == 10 ||
tinf->trans_table == 14 || tinf->trans_table == 15 ||
tinf->trans_table == 16 || tinf->trans_table == 22) return 0;
/* GTG */
if(is_g(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 1 || tinf->trans_table == 3 ||
tinf->trans_table == 12 || tinf->trans_table == 22) return 0;
return 1;
}
/* TTG */
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table < 4 || tinf->trans_table == 9 ||
tinf->trans_table >= 21) return 0;
return 1;
}
/* We do not handle other initiation codons */
return 0;
}
double gc_content(unsigned char *seq, int a, int b) {
double sum = 0.0, gc = 0.0;
int i;
for(i = a; i <= b; i++) {
if(is_g(seq, i) == 1 || is_c(seq, i) == 1) gc++;
sum++;
}
return gc/sum;
}
int is_stop(unsigned char *seq, int n, struct _training *tinf) {
/* TAG */
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 15 ||
tinf->trans_table == 16 || tinf->trans_table == 22) return 0;
return 1;
}
/* TGA */
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if((tinf->trans_table >= 2 && tinf->trans_table <= 5) ||
tinf->trans_table == 9 || tinf->trans_table == 10 ||
tinf->trans_table == 13 || tinf->trans_table == 14 ||
tinf->trans_table == 21) return 0;
return 1;
}
/* TAA */
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 14) return 0;
return 1;
}
/* Code 2 */
if(tinf->trans_table == 2 && is_a(seq, n) == 1 && is_g(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
if(tinf->trans_table == 2 && is_a(seq, n) == 1 && is_g(seq, n+1) == 1 &&
is_g(seq, n+2) == 1) return 1;
/* Code 22 */
if(tinf->trans_table == 22 && is_t(seq, n) == 1 && is_c(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
/* Code 23 */
if(tinf->trans_table == 23 && is_t(seq, n) == 1 && is_t(seq, n+1) == 1 &&
is_a(seq, n+2) == 1) return 1;
return 0;
}
//======================================================================
bool sccan_point_pair_handler::
is_string_a_sccan_run_config(std::string line){
if(verbosity){
std::cout<<"sccan_point_pair_handler -> ";
std::cout<<"is_string_a_sccan_run_config() -> line: ";
std::cout<<line<<std::endl;
}
// use DEAs for the std::string control
// find
enum TokenT{
digit,
point,
underscore,
char_c,
char_f,
char_g,
char_s,
char_a,
char_n,
ERR
};
int GetState[][23] ={
//dig point under c f g s a n
{ 1, -1, -1, -1, -1, -1, -1, -1, -1 }, //0 d
{ 2, -1, -1, -1, -1, -1, -1, -1, -1 }, //1 d
{ 3, -1, -1, -1, -1, -1, -1, -1, -1 }, //2 d
{ 4, -1, -1, -1, -1, -1, -1, -1, -1 }, //3 d
{ 5, -1, -1, -1, -1, -1, -1, -1, -1 }, //4 d
{ 6, -1, -1, -1, -1, -1, -1, -1, -1 }, //5 d
{ 7, -1, -1, -1, -1, -1, -1, -1, -1 }, //6 d
{ 8, -1, -1, -1, -1, -1, -1, -1, -1 }, //7 d
{ -1, -1, 9, -1, -1, -1, -1, -1, -1 }, //8 _
{ 10, -1, -1, -1, -1, -1, -1, -1, -1 }, //9 d
{ 11, -1, -1, -1, -1, -1, -1, -1, -1 }, //10 d
{ 12, -1, -1, -1, -1, -1, -1, -1, -1 }, //11 d
{ 13, -1, -1, -1, -1, -1, -1, -1, -1 }, //12 d
{ -1, -1, 14, -1, -1, -1, -1, -1, -1 }, //13 _
{ -1, -1, -1, -1, -1, -1, 15, -1, -1 }, //14 s
{ -1, -1, -1, 16, -1, -1, -1, -1, -1 }, //15 c
{ -1, -1, -1, 17, -1, -1, -1, -1, -1 }, //16 c
{ -1, -1, -1, -1, -1, -1, -1, 18, -1 }, //17 a
{ -1, -1, -1, -1, -1, -1, -1, -1, 19 }, //18 n
{ -1, -1, 20, -1, -1, -1, -1, -1, -1 }, //19 _
{ 20, 21, -1, -1, -1, -1, -1, -1, -1 }, //20 d
{ -1, -1, -1, 22, -1, -1, -1, -1, -1 }, //21 .
{ -1, -1, -1, -1, 23, -1, -1, -1, -1 }, //22 c
{ -1, -1, -1, -1, -1, 24, -1, -1, -1 }, //23 f
//24 g
};
//for( int i=0; i<11;i++){std::cout<<"("<<i<<")"<<GetState[26][i]<<", ";}
//std::cout<<std::endl;
std::string ID;
std::string tilt_x;
std::string tilt_y;
std::string tilt_z;
std::string str_vec2D_x;
std::string str_vec2D_y;
int int_vec2D_count = 0;
int state = 0;
int char_number = 0;
//std::cout<<"str laenge: "<<line.size()<<std::endl;
while(state != -1 && char_number<line.size()){
TokenT token = ERR;
char s = line.at( char_number);
if(is_c(s)) token = char_c;
if(is_f(s)) token = char_f;
if(is_g(s)) token = char_g;
if(is_s(s)) token = char_s;
if(is_a(s)) token = char_a;
if(is_n(s)) token = char_n;
if(isdigit(s)) token = digit;
//std::cout<<char(s)<<"==digit"<<std::endl;}
if(is_point(s)) token = point;
if(is_underscore(s)) token = underscore;
//std::cout<<"check"<<char_number<<": ";
//std::cout<<char(s)<<" state: "<<state<<" token: "<<token<<std::endl;
state = (token == ERR) ? :GetState[state][token];
char_number ++;
}
if(state==24){return true;}else{return false;};
}
int shine_dalgarno_mm(unsigned char *seq, int pos, int start, double *rwt) {
int i, j, k, mism, rdis, limit, max_val, cur_val = 0;
double match[6], cur_ctr, dis_flag;
limit = imin(6, start-4-pos);
for(i = limit; i < 6; i++) match[i] = -10.0;
/* Compare the 6-base region to AGGAGG */
for(i = 0; i < limit; i++) {
if(pos+i < 0) continue;
if(i % 3 == 0) {
if(is_a(seq, pos+i) == 1) match[i] = 2.0;
else match[i] = -3.0;
}
else {
if(is_g(seq, pos+i) == 1) match[i] = 3.0;
else match[i] = -2.0;
}
}
/* Find the maximally scoring motif */
max_val = 0;
for(i = limit; i >= 5; i--) {
for(j = 0; j <= limit-i; j++) {
cur_ctr = -2.0;
mism = 0;
for(k = j; k < j+i; k++) {
cur_ctr += match[k];
if(match[k] < 0.0) mism++;
if(match[k] < 0.0 && (k <= j+1 || k >= j+i-2)) cur_ctr -= 10.0;
}
if(mism != 1) continue;
rdis = start - (pos+j+i);
if(rdis < 5) { dis_flag = 1; }
else if(rdis > 10 && rdis <= 12) { dis_flag = 2; }
else if(rdis >= 13) { dis_flag = 3; }
else dis_flag = 0;
if(rdis > 15 || cur_ctr < 6.0) continue;
/* Single-Mismatch RBS Motifs */
if(cur_ctr < 6.0) cur_val = 0;
else if(cur_ctr == 6.0 && dis_flag == 3) cur_val = 2;
else if(cur_ctr == 7.0 && dis_flag == 3) cur_val = 2;
else if(cur_ctr == 9.0 && dis_flag == 3) cur_val = 3;
else if(cur_ctr == 6.0 && dis_flag == 2) cur_val = 4;
else if(cur_ctr == 6.0 && dis_flag == 1) cur_val = 5;
else if(cur_ctr == 6.0 && dis_flag == 0) cur_val = 9;
else if(cur_ctr == 7.0 && dis_flag == 2) cur_val = 7;
else if(cur_ctr == 7.0 && dis_flag == 1) cur_val = 8;
else if(cur_ctr == 7.0 && dis_flag == 0) cur_val = 14;
else if(cur_ctr == 9.0 && dis_flag == 2) cur_val = 17;
else if(cur_ctr == 9.0 && dis_flag == 1) cur_val = 18;
else if(cur_ctr == 9.0 && dis_flag == 0) cur_val = 19;
if(rwt[cur_val] < rwt[max_val]) continue;
if(rwt[cur_val] == rwt[max_val] && cur_val < max_val) continue;
max_val = cur_val;
}
}
return max_val;
}
int shine_dalgarno_exact(unsigned char *seq, int pos, int start, double *rwt) {
int i, j, k, mism, rdis, limit, max_val, cur_val = 0;
double match[6], cur_ctr, dis_flag;
limit = imin(6, start-4-pos);
for(i = limit; i < 6; i++) match[i] = -10.0;
/* Compare the 6-base region to AGGAGG */
for(i = 0; i < limit; i++) {
if(pos+i < 0) continue;
if(i%3 == 0 && is_a(seq, pos+i) == 1) match[i] = 2.0;
else if(i%3 != 0 && is_g(seq, pos+i) == 1) match[i] = 3.0;
else match[i] = -10.0;
}
/* Find the maximally scoring motif */
max_val = 0;
for(i = limit; i >= 3; i--) {
for(j = 0; j <= limit-i; j++) {
cur_ctr = -2.0;
mism = 0;
for(k = j; k < j+i; k++) {
cur_ctr += match[k];
if(match[k] < 0.0) mism++;
}
if(mism > 0) continue;
rdis = start - (pos+j+i);
if(rdis < 5 && i < 5) dis_flag = 2;
else if(rdis < 5 && i >= 5) dis_flag = 1;
else if(rdis > 10 && rdis <= 12 && i < 5) dis_flag = 1;
else if(rdis > 10 && rdis <= 12 && i >= 5) dis_flag = 2;
else if(rdis >= 13) { dis_flag = 3; }
else dis_flag = 0;
if(rdis > 15 || cur_ctr < 6.0) continue;
/* Exact-Matching RBS Motifs */
if(cur_ctr < 6.0) cur_val = 0;
else if(cur_ctr == 6.0 && dis_flag == 2) cur_val = 1;
else if(cur_ctr == 6.0 && dis_flag == 3) cur_val = 2;
else if(cur_ctr == 8.0 && dis_flag == 3) cur_val = 3;
else if(cur_ctr == 9.0 && dis_flag == 3) cur_val = 3;
else if(cur_ctr == 6.0 && dis_flag == 1) cur_val = 6;
else if(cur_ctr == 11.0 && dis_flag == 3) cur_val = 10;
else if(cur_ctr == 12.0 && dis_flag == 3) cur_val = 10;
else if(cur_ctr == 14.0 && dis_flag == 3) cur_val = 10;
else if(cur_ctr == 8.0 && dis_flag == 2) cur_val = 11;
else if(cur_ctr == 9.0 && dis_flag == 2) cur_val = 11;
else if(cur_ctr == 8.0 && dis_flag == 1) cur_val = 12;
else if(cur_ctr == 9.0 && dis_flag == 1) cur_val = 12;
else if(cur_ctr == 6.0 && dis_flag == 0) cur_val = 13;
else if(cur_ctr == 8.0 && dis_flag == 0) cur_val = 15;
else if(cur_ctr == 9.0 && dis_flag == 0) cur_val = 16;
else if(cur_ctr == 11.0 && dis_flag == 2) cur_val = 20;
else if(cur_ctr == 11.0 && dis_flag == 1) cur_val = 21;
else if(cur_ctr == 11.0 && dis_flag == 0) cur_val = 22;
else if(cur_ctr == 12.0 && dis_flag == 2) cur_val = 20;
else if(cur_ctr == 12.0 && dis_flag == 1) cur_val = 23;
else if(cur_ctr == 12.0 && dis_flag == 0) cur_val = 24;
else if(cur_ctr == 14.0 && dis_flag == 2) cur_val = 25;
else if(cur_ctr == 14.0 && dis_flag == 1) cur_val = 26;
else if(cur_ctr == 14.0 && dis_flag == 0) cur_val = 27;
if(rwt[cur_val] < rwt[max_val]) continue;
if(rwt[cur_val] == rwt[max_val] && cur_val < max_val) continue;
max_val = cur_val;
}
}
return max_val;
}
/* Returns a single amino acid for this position */
char amino(unsigned char *seq, int n, struct _training *tinf, int is_init) {
if(is_stop(seq, n, tinf) == 1) return '*';
if(is_start(seq, n, tinf) == 1 && is_init == 1) return 'M';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'F';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'F';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'L';
if(is_t(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'L';
if(is_t(seq, n) == 1 && is_c(seq, n+1) == 1) return 'S';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'Y';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'Y';
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 6) return 'Q';
if(tinf->trans_table == 14) return 'Y';
}
if(is_t(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 6 || tinf->trans_table == 15) return 'Q';
if(tinf->trans_table == 22) return 'L';
}
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'C';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'C';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'W';
if(is_t(seq, n) == 1 && is_g(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'W';
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
return 'L';
}
if(is_c(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1) {
if(tinf->trans_table == 3) return 'T';
if(tinf->trans_table == 12) return 'S';
return 'L';
}
if(is_c(seq, n) == 1 && is_c(seq, n+1) == 1) return 'P';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'H';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'H';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'Q';
if(is_c(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'Q';
if(is_c(seq, n) == 1 && is_g(seq, n+1) == 1) return 'R';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'I';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'I';
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 2 || tinf->trans_table == 3 ||
tinf->trans_table == 5 || tinf->trans_table == 13 ||
tinf->trans_table == 21) return 'M';
return 'I';
}
if(is_a(seq, n) == 1 && is_t(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'M';
if(is_a(seq, n) == 1 && is_c(seq, n+1) == 1) return 'T';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'N';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'N';
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1) {
if(tinf->trans_table == 9 || tinf->trans_table == 14 ||
tinf->trans_table == 21) return 'N';
return 'K';
}
if(is_a(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'K';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'S';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'S';
if(is_a(seq, n) == 1 && is_g(seq, n+1) == 1 && (is_a(seq, n+2) == 1 ||
is_g(seq, n+2) == 1)) {
if(tinf->trans_table == 13) return 'G';
if(tinf->trans_table == 5 || tinf->trans_table == 9 ||
tinf->trans_table == 14 || tinf->trans_table == 21) return 'S';
return 'R';
}
if(is_g(seq, n) == 1 && is_t(seq, n+1) == 1) return 'V';
if(is_g(seq, n) == 1 && is_c(seq, n+1) == 1) return 'A';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_t(seq, n+2) == 1)
return 'D';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_c(seq, n+2) == 1)
return 'D';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_a(seq, n+2) == 1)
return 'E';
if(is_g(seq, n) == 1 && is_a(seq, n+1) == 1 && is_g(seq, n+2) == 1)
return 'E';
if(is_g(seq, n) == 1 && is_g(seq, n+1) == 1) return 'G';
return 'X';
}
int is_ttg(unsigned char *seq, int n) {
if(is_t(seq, n) == 0 || is_t(seq, n+1) == 0 || is_g(seq, n+2) == 0) return 0;
return 1;
}